DeepAI AI Chat
Log In Sign Up

Visual Odometry Revisited: What Should Be Learnt?

by   Huangying Zhan, et al.

In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be carefully designed for different application scenarios. Moreover, most monocular systems suffer from scale-drift issue. Some recent deep learning works learn VO in an end-to-end manner but the performance of these deep systems is still not comparable to geometry-based methods. In this work, we revisit the basics of VO and explore the right way for integrating deep learning with epipolar geometry and Perspective-n-Point (PnP) method. Specifically, we train two convolutional neural networks (CNNs) for estimating single-view depths and two-view optical flows as intermediate outputs. With the deep predictions, we design a simple but robust frame-to-frame VO algorithm (DF-VO) which outperforms pure deep learning-based and geometry-based methods. More importantly, our system does not suffer from the scale-drift issue being aided by a scale consistent single-view depth CNN. Extensive experiments on KITTI dataset shows the robustness of our system and a detailed ablation study shows the effect of different factors in our system.


DF-VO: What Should Be Learnt for Visual Odometry?

Multi-view geometry-based methods dominate the last few decades in monoc...

WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks

In this work we present WGANVO, a Deep Learning based monocular Visual O...

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

Despite learning based methods showing promising results in single view ...

DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks

This paper studies monocular visual odometry (VO) problem. Most of exist...

Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning

Inspired by the cognitive process of humans and animals, Curriculum Lear...

Deep Online Correction for Monocular Visual Odometry

In this work, we propose a novel deep online correction (DOC) framework ...

Bayesian Scale Estimation for Monocular SLAM Based on Generic Object Detection for Correcting Scale Drift

This work proposes a new, online algorithm for estimating the local scal...